pipeline.sh in lederhosen-0.1.1 vs pipeline.sh in lederhosen-0.1.2

@@ -1,37 +1,71 @@
 #!/bin/bash
 
-set +e
-
 # An example OTU clustering pipeline
 # Austin G. Davis-Richardson
 # <harekrishna at gmail dot com>
+# http://github.com/audy/lederhosen
 
-raw_reads='raw_reads/*.txt'
-identities='0.975'
+set -e
+
+raw_reads='spec/data/*.txt'
 out_dir='pipeline'
+taxcollector='taxcollector.fa'
+min_reads=50
+min_samples=10
 
 # trim reads
-bin/lederhosen trim --reads-dir=$raw_reads --out-dir=$out_dir/trimmed
+bin/lederhosen trim \
+               --reads-dir=$raw_reads \
+               --out-dir=$out_dir/trimmed
 
 # join reads
-bin/lederhosen join --trimmed=$out_dir/trimmed/*.fasta --output=$out_dir/joined.fasta
+bin/lederhosen join \
+               --trimmed=$out_dir/trimmed/*.fasta \
+               --output=$out_dir/joined.fasta
 
 # filter reads
-bin/lederhosen filter --input=$out_dir/joined.fasta --output=$out_dir/filtered.fasta -k=10 --cutoff=50
+bin/lederhosen k_filter \
+               --input=$out_dir/joined.fasta \
+               --output=$out_dir/filtered.fasta \
+               -k=10 \
+               --cutoff=50
 
 # sort
-bin/lederhosen sort --input=$out_dir/filtered.fasta --output=$out_dir/sorted.fasta
+bin/lederhosen sort \
+               --input=$out_dir/filtered.fasta \
+               --output=$out_dir/sorted.fasta
 
-# cluster
-for i in $identities
+for i in 0.80 0.90 0.95
 do
-    bin/lederhosen cluster --input=$out_dir/sorted.fasta --output=$out_dir/clusters_"$i"_.uc --identity=$i
-done
+    # cluster
+    bin/lederhosen cluster \
+                   --input=$out_dir/sorted.fasta \
+                   --output=$out_dir/clusters_"$i".uc \
+                   --identity=$i
 
-# generate otu tables
-for i in $identities
-do
-    bin/lederhosen otu_table --clusters=$out_dir/clusters_"$i"_.uc --output=$out_dir/otus_"$i"
+    # filter uc file
+    bin/lederhosen uc_filter \
+                   --input=$out_dir/clusters_"$i".uc \
+                   --output=$out_dir/clusters_"$i".uc.filtered \
+                   --reads=$min_reads \
+                   --samples=$min_samples \
+
+    # generate otu table
+    bin/lederhosen otu_table \
+                   --clusters=$out_dir/clusters_"$i".uc.filtered \
+                   --output=$out_dir/otus_"$i"
+
+    # get representative reads
+    bin/lederhosen rep_reads \
+                   --clusters=$out_dir/clusters_"$i".uc.filtered \
+                   --joined=$out_dir/sorted.fasta \
+                   --output=$out_dir/representatives_"$i".fasta
+
+    # blast representative reads
+    bin/lederhosen name \
+                   --reps=$out_dir/representatives_"$i".fasta \
+                   --output=$out_dir/taxonomies_"$i".txt \
+                   --database=$taxcollector
 done
 
 echo "complete!"
\ No newline at end of file